metadata
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
metrics:
- f1
model-index:
- name: vit-base-beans-demo-v5
results: []
vit-base-beans-demo-v5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the rvl-cdip, the cord, the receipts and the coco datasets. It achieves the following results on the evaluation set:
- Loss: 0.0017
- F1: 0.9990
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.0033 | 0.23 | 100 | 0.0032 | 1.0 |
| 0.0017 | 0.45 | 200 | 0.0018 | 1.0 |
| 0.0012 | 0.68 | 300 | 0.0020 | 0.9990 |
| 0.001 | 0.91 | 400 | 0.0017 | 0.9990 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.11.0+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1